* segment sizes marked with an asterisk are estimates pending a measured run
Estimated per-node footprint, weights + KV sharded across the Spark (tensor parallel). Overhead ~8 GB/node; KV at FP16.
one MoE layer · 256 experts, 8 fire per token
each expert ≈ 3M params
resident: 40 MoE layers × 256 experts × 3M ≈ 32.2B
active/token: 40 × 8 × 3M ≈ 1.0B experts
+ 2.4B always-on dense (attention, embeddings, shared stack) = 3.5B active
Recipes (all recipes)
Worked deployments that run this model on DGX Spark — each shows how it fills each node's unified memory.
Qwen AgentWorld 35B-A3B — BF16
Qwen's agentic AgentWorld 35B-A3B (35B MoE, ~3B active) unquantized in BF16 on one DGX Spark, serving the full 262,144-token context at 30.4 tok/s single-stream.
Qwen AgentWorld 35B-A3B — NVFP4
Qwen's agentic AgentWorld 35B-A3B (35B MoE, ~3B active) in NVFP4 on one DGX Spark, serving the full 262,144-token context at 83.1 tok/s single-stream with Qwen3.6's MTP head grafted in.
Optimize
35B params, ~69 GB at bfloat16 — fits on one Spark as-is.
Make it fit
Get the weights (and headroom for KV) inside the 128 GB pool — the hard gate.
Lossless compression
BF16 weights entropy-code ~30% smaller bit-exact — smaller downloads and less bandwidth per token, no quality question at all.
Make it fast
Once it fits: fewer bytes per token and fewer decode steps against 273 GB/s.
Add a speculative decoder
Decode is bandwidth-bound at ~39.5 tok/s ceiling; a trained EAGLE-style draft multiplies tokens per weight-read.
Prune experts for speed
Fewer experts ⇒ smaller working set ⇒ better cache/page behavior, even when it already fits.
Tame the KV cache
At 262144 tokens the KV cache alone is ~21 GB at FP16; quantize or evict.
Make it yours
Change what the model does — adapt, edit, or steer it — independent of size.
Fine-tune it
LoRA/QLoRA adapts behavior on one Spark without touching the base weights.
Edit or steer it
One-shot weight math — no gradients, no corpus.